Hongyan Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hongyan Liu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Guangtao Zhai
Shanghai Jiao Tong University
4 shared publications - Ke Gu
Beijing University of Technology
4 shared publications - Lai-Kuan Wong
Faculty of Computing and Informatics, Multimedia University, Cyberjaya, Selangor, Malaysia
3 shared publications - Weisi Lin
Nanyang Technological University
3 shared publications - Wenjun Zhang
Shanghai Jiao Tong University
3 shared publications Shu Jin
School of Artificial Intelligence and the Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education, Beijing University of Technology, Beijing, China
2 shared publications
Latest Publications
- 27 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 72 (2) , 505-519
A Highly Efficient Zero-Shot Image Denoiser
Currently, there is an increasingly high demand for high-quality images across various streaming media applications, but visual signals are impaired by composite noise. The existing dataset-based image denoisers, requiring a huge number of clean-noisy image pairs from diverse scenes to well train a large-size deep network, often perform unwell in the real-world noisy image restoration due to the complexity and variability of scenes, limited computing resources and the difficulty in obtaining clean images. So this paper tries to propose a dataset-free highly efficient zero-shot image denoiser with a lightweight CNN, called HEZID, to achieve the effective real-time real-world noisy image restoration. First, for the problem of the BSN strategy that discards the center pixel to avoid identity mapping for image denoising, we propose a new solution by devising a dual-mode pixel-realignment strategy, which sequentially develops a ‘rough’ pixel-realignment method for smooth regions and a ‘fine’ pixel-realignment method for edge regions, therefore fully exploiting the center pixel and preventing identity mapping. Second, we develop a super-lightweight CNN-based denoiser based on the strip convolution, which is motivated by the high sensitivity of human eyes to horizontal and vertical stimuli for visual inputs, followed by introducing the residual learning and separable convolutions to severally facilitate feature propagation and reduce the computational burden. Experiments on multiple real-world noisy image datasets confirmed that our HEZID outperformed a dozen state-of-the-art peers in terms of restoration quality and running efficiency.
- 27 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Broadcasting
- Vol. 72 (2) , 505-519
A Highly Efficient Zero-Shot Image Denoiser
Currently, there is an increasingly high demand for high-quality images across various streaming media applications, but visual signals are impaired by composite noise. The existing dataset-based image denoisers, requiring a huge number of clean-noisy image pairs from diverse scenes to well train a large-size deep network, often perform unwell in the real-world noisy image restoration due to the complexity and variability of scenes, limited computing resources and the difficulty in obtaining clean images. So this paper tries to propose a dataset-free highly efficient zero-shot image denoiser with a lightweight CNN, called HEZID, to achieve the effective real-time real-world noisy image restoration. First, for the problem of the BSN strategy that discards the center pixel to avoid identity mapping for image denoising, we propose a new solution by devising a dual-mode pixel-realignment strategy, which sequentially develops a ‘rough’ pixel-realignment method for smooth regions and a ‘fine’ pixel-realignment method for edge regions, therefore fully exploiting the center pixel and preventing identity mapping. Second, we develop a super-lightweight CNN-based denoiser based on the strip convolution, which is motivated by the high sensitivity of human eyes to horizontal and vertical stimuli for visual inputs, followed by introducing the residual learning and separable convolutions to severally facilitate feature propagation and reduce the computational burden. Experiments on multiple real-world noisy image datasets confirmed that our HEZID outperformed a dozen state-of-the-art peers in terms of restoration quality and running efficiency.
- Top Cited Papers
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7909-7920
A Lightweight Deep and Wide Network for Image-Based Detection of Industrial Waste Gas
Due to inadequate monitoring, key pollutants (e.g., PM2.5, VOCs, etc) very possibly leak into atmosphere, thus to endanger the long-term and short-term life safety of people that work and live in the environment. Therefore, it is imperative to effectively and efficiently detect the leakage of industrial waste gas, for the purpose of timely lowering the risk of pollution and explosions. To solve such a problem, we in this paper propose a new lightweight deep and wide network (LdwNet) for detecting the leakage of industrial waste gas from an image, which brings about the two main merits: 1) Compensating for the deficiencies of sensor-based detection methods, which can accurately detect the leakage of waste gas and even measure its concentrations but require to seek leakage sources beforehand; 2) Overcoming the shortcomings of image-based detection methods, which leverage DNN-based recognition technologies and usually suffer from low efficacy, low efficiency and high energy consumption during the model training and inference. To specify, the proposed LdwNet is developed by simulating human perception, motivated by the method which detects the leakage of industrial waste gas from surveillance images with the human observation and judgement. First, based on the inspiration that the human eyes are highly sensitive to horizontal and vertical stimuli, we construct a novel lightweight parallel-series-stripe (PS2) module to validly extract features with very few parameters. Second, to fully exploit deep and shallow features for fusing the global and local information, we extend the PS2 module as a backbone along both the deep and wide directions to build the multi-channel network. Third, to achieve effective, efficient and low-carbon detection in model running, we constraint the extended PS2 modules with parameter sharing to prodigiously reduce the model parameters and thus to make the proposed model ultra-lightweight. Experiments on the datasets of carbon particulate matters and ethylene leakage prove that our LdwNet with ten thousand parameters outperforms the state-of-the-art models with millions of parameters in detection accuracy and implementation cost, and this renders our proposed LdwNet more suitable for real industrial applications.
- 26 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7909-7920
Top Cited PapersA Lightweight Deep and Wide Network for Image-Based Detection of Industrial Waste Gas
Due to inadequate monitoring, key pollutants (e.g., PM2.5, VOCs, etc) very possibly leak into atmosphere, thus to endanger the long-term and short-term life safety of people that work and live in the environment. Therefore, it is imperative to effectively and efficiently detect the leakage of industrial waste gas, for the purpose of timely lowering the risk of pollution and explosions. To solve such a problem, we in this paper propose a new lightweight deep and wide network (LdwNet) for detecting the leakage of industrial waste gas from an image, which brings about the two main merits: 1) Compensating for the deficiencies of sensor-based detection methods, which can accurately detect the leakage of waste gas and even measure its concentrations but require to seek leakage sources beforehand; 2) Overcoming the shortcomings of image-based detection methods, which leverage DNN-based recognition technologies and usually suffer from low efficacy, low efficiency and high energy consumption during the model training and inference. To specify, the proposed LdwNet is developed by simulating human perception, motivated by the method which detects the leakage of industrial waste gas from surveillance images with the human observation and judgement. First, based on the inspiration that the human eyes are highly sensitive to horizontal and vertical stimuli, we construct a novel lightweight parallel-series-stripe (PS2) module to validly extract features with very few parameters. Second, to fully exploit deep and shallow features for fusing the global and local information, we extend the PS2 module as a backbone along both the deep and wide directions to build the multi-channel network. Third, to achieve effective, efficient and low-carbon detection in model running, we constraint the extended PS2 modules with parameter sharing to prodigiously reduce the model parameters and thus to make the proposed model ultra-lightweight. Experiments on the datasets of carbon particulate matters and ethylene leakage prove that our LdwNet with ten thousand parameters outperforms the state-of-the-art models with millions of parameters in detection accuracy and implementation cost, and this renders our proposed LdwNet more suitable for real industrial applications.
- Top Cited Papers
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2238-2252
Infrared Image Quality Estimation With Node-to-Graph Regression
By comparison with the commonly seen visible light images that can be effectively characterized within a Euclidean space, infrared images have non-Euclidean characteristics since their pixels contain rich thermal radiation information, such as heat distribution, surface temperature and thermal radiation. Considering the advantages of Graph Convolutional Networks (GCNs) in processing non-Euclidean data, this study proposes to introduce the GCNs to estimate the quality of infrared images by developing the Node-to-Graph Regression (NGR) model. To specify, the proposed NGR model is composed of two main steps, namely network establishment and network training. In the first step, following the classical researches of image quality estimation that include local distortion measurement followed by pooling for inferring the image quality score, this study captures the local distortion of the input infrared images by stacking up a set of Vision Graph (VSG) blocks to generate one node map, and then conducts the weighted pooling method on the node map to yield the graph output as the estimated quality score. In the second step, for enhancing the model's performance and generalization ability in the network training process, this study implements the node regression with the big data pre-training method to raise the local distortion extraction ability in a broad range of image scenarios and distortion intensities, and then performs the graph regression by using the knowledge distillation method to reduce the over-fitting risk. Using the largest-size infrared image quality evaluation database (I2QED), this study compared the proposed NGR model with three dozen mainstream and state-of-the-art competitors, and results showed that our proposed NGR model achieved the optimal performance.
- 12 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28 (15209210) , 2238-2252
Top Cited PapersInfrared Image Quality Estimation With Node-to-Graph Regression
By comparison with the commonly seen visible light images that can be effectively characterized within a Euclidean space, infrared images have non-Euclidean characteristics since their pixels contain rich thermal radiation information, such as heat distribution, surface temperature and thermal radiation. Considering the advantages of Graph Convolutional Networks (GCNs) in processing non-Euclidean data, this study proposes to introduce the GCNs to estimate the quality of infrared images by developing the Node-to-Graph Regression (NGR) model. To specify, the proposed NGR model is composed of two main steps, namely network establishment and network training. In the first step, following the classical researches of image quality estimation that include local distortion measurement followed by pooling for inferring the image quality score, this study captures the local distortion of the input infrared images by stacking up a set of Vision Graph (VSG) blocks to generate one node map, and then conducts the weighted pooling method on the node map to yield the graph output as the estimated quality score. In the second step, for enhancing the model's performance and generalization ability in the network training process, this study implements the node regression with the big data pre-training method to raise the local distortion extraction ability in a broad range of image scenarios and distortion intensities, and then performs the graph regression by using the knowledge distillation method to reduce the over-fitting risk. Using the largest-size infrared image quality evaluation database (I2QED), this study compared the proposed NGR model with three dozen mainstream and state-of-the-art competitors, and results showed that our proposed NGR model achieved the optimal performance.